QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
arXiv preprint arXiv:2406.16863 (2024) 18 Meric et al
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
background 2polarities
background 2representative citing papers
TrajLoc enforces per-object trajectory constraints in I2V generation via attention-layer Gaussian heatmap substitution, yielding +4.3 dB PSNR and 51% lower endpoint error on datasets with up to 20 objects across two backbones.
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
Go-with-the-Track unifies multi-reference compositing and point-track motion control in video diffusion by using spatially-aware point-track embeddings injected via an adapter.
NTRK is a reward-guided diffusion sampler that uses a whitening operator to bias the noise term toward high-reward outcomes, outperforming baselines with up to 20x fewer sampling steps on aesthetic tasks.
EverAnimate restores drifted latent flow trajectories in chunked video generation via persistent latent propagation and restorative flow matching, achieving measurable gains in PSNR, SSIM, LPIPS, and FID over prior long-animation methods with only LoRA tuning.
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
Sparse 3D hand joints plus an occlusion-aware control module produce higher-fidelity, 3D-consistent egocentric hand-object videos than dense-2D or implicit-pose baselines.
MotionAdapter transfers reference video motions into target videos inside DiT diffusion models by isolating attention-derived motion fields and refining them via DINO-guided semantic alignment.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
-
TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
TrajLoc enforces per-object trajectory constraints in I2V generation via attention-layer Gaussian heatmap substitution, yielding +4.3 dB PSNR and 51% lower endpoint error on datasets with up to 20 objects across two backbones.
-
CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration
CoMoGen generates controllable interactive video from mask sequences and images by encoding masks into MMDiT via MaskAdapter and LoRA on motion layers, claiming SOTA motion fidelity.
-
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Go-with-the-Track unifies multi-reference compositing and point-track motion control in video diffusion by using spatially-aware point-track embeddings injected via an adapter.
-
NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment
NTRK is a reward-guided diffusion sampler that uses a whitening operator to bias the noise term toward high-reward outcomes, outperforming baselines with up to 20x fewer sampling steps on aesthetic tasks.
-
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
EverAnimate restores drifted latent flow trajectories in chunked video generation via persistent latent propagation and restorative flow matching, achieving measurable gains in PSNR, SSIM, LPIPS, and FID over prior long-animation methods with only LoRA tuning.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
Sparse 3D hand joints plus an occlusion-aware control module produce higher-fidelity, 3D-consistent egocentric hand-object videos than dense-2D or implicit-pose baselines.
-
MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
MotionAdapter transfers reference video motions into target videos inside DiT diffusion models by isolating attention-derived motion fields and refining them via DINO-guided semantic alignment.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.